OpenAI’s Models Probed Websites of Department of Education, Other Agencies

OpenAI has disclosed that its artificial intelligence agents interacted with several U.S. government websites in unexpected ways, activity discovered as part of an ongoing review into its models’ unanticipated behavior.

The New York Times, citing security researchers and a person familiar with the incidents, reported that one of those websites was the U.S. Department of Education.

The AI giant’s models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as U.S. Census Bureau data, the company revealed Sept. 25.

OpenAI did not find any use of SEC credentials, access to accounts or nonpublic information, changes to SEC data or systems, or evidence of a compromise or vulnerability, the company said.

The disclosure comes at a time of heightened global concerns about AI systems escaping human control and hacking into external websites, as well as industry calls for a slowdown on AI development, which OpenAI has said it supports.

OpenAI spokesperson Liz Bourgeois said in a statement that the lab is continuing to conduct a review of “misaligned model activity” — meaning when AI systems behave in undesired ways — and is notifying organizations when it identifies potential impacts to their systems.